Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 1962 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.3613. Min Range: -4.3613

Max Act: 4.3613. Min Act: -0.1700

Data Index: 4823744 (Open Web Text)

Max Activating Token Index: 269

Text #1

Max Range: 4.3613. Min Range: -4.3613

Max Act: 4.3158. Min Act: -0.1700

Data Index: 485 (Open Web Text)

Max Activating Token Index: 590

Text #2

Max Range: 4.3613. Min Range: -4.3613

Max Act: 4.2654. Min Act: -0.1700

Data Index: 601283 (Open Web Text)

Max Activating Token Index: 51

Text #3

Max Range: 4.3613. Min Range: -4.3613

Max Act: 4.2637. Min Act: -0.1700

Data Index: 4918507 (Open Web Text)

Max Activating Token Index: 826

Text #4

Max Range: 4.3613. Min Range: -4.3613

Max Act: 4.2800. Min Act: -0.1700

Data Index: 2986752 (Open Web Text)

Max Activating Token Index: 965

Text #5

Max Range: 4.3613. Min Range: -4.3613

Max Act: 4.2375. Min Act: -0.1700

Data Index: 8652679 (Open Web Text)

Max Activating Token Index: 635

Text #6

Max Range: 4.3613. Min Range: -4.3613

Max Act: 4.2280. Min Act: -0.1700

Data Index: 7765194 (Open Web Text)

Max Activating Token Index: 408

Text #7

Max Range: 4.3613. Min Range: -4.3613

Max Act: 4.2339. Min Act: -0.1700

Data Index: 7459550 (Open Web Text)

Max Activating Token Index: 218

Text #8

Max Range: 4.3613. Min Range: -4.3613

Max Act: 4.2311. Min Act: -0.1700

Data Index: 7087503 (Open Web Text)

Max Activating Token Index: 581

Text #9

Max Range: 4.3613. Min Range: -4.3613

Max Act: 4.2315. Min Act: -0.1700

Data Index: 5059837 (Open Web Text)

Max Activating Token Index: 1014

Text #10

Max Range: 4.3613. Min Range: -4.3613

Max Act: 4.1915. Min Act: -0.1700

Data Index: 5850134 (Open Web Text)

Max Activating Token Index: 470

Text #11

Max Range: 4.3613. Min Range: -4.3613

Max Act: 4.2030. Min Act: -0.1700

Data Index: 6429921 (Open Web Text)

Max Activating Token Index: 223

Text #12

Max Range: 4.3613. Min Range: -4.3613

Max Act: 4.1791. Min Act: -0.1700

Data Index: 6939434 (Open Web Text)

Max Activating Token Index: 690

Text #13

Max Range: 4.3613. Min Range: -4.3613

Max Act: 4.1775. Min Act: -0.1700

Data Index: 6981158 (Open Web Text)

Max Activating Token Index: 915

Text #14

Max Range: 4.3613. Min Range: -4.3613

Max Act: 4.2156. Min Act: -0.1700

Data Index: 5481053 (Open Web Text)

Max Activating Token Index: 730

Text #15

Max Range: 4.3613. Min Range: -4.3613

Max Act: 4.1707. Min Act: -0.1700

Data Index: 5203572 (Open Web Text)

Max Activating Token Index: 612

Text #16

Max Range: 4.3613. Min Range: -4.3613

Max Act: 4.2080. Min Act: -0.1700

Data Index: 2006877 (Open Web Text)

Max Activating Token Index: 660

Text #17

Max Range: 4.3613. Min Range: -4.3613

Max Act: 4.1897. Min Act: -0.1700

Data Index: 7739369 (Open Web Text)

Max Activating Token Index: 163

Text #18

Max Range: 4.3613. Min Range: -4.3613

Max Act: 4.2185. Min Act: -0.1700

Data Index: 3966802 (Open Web Text)

Max Activating Token Index: 244

Text #19

Max Range: 4.3613. Min Range: -4.3613

Max Act: 4.2051. Min Act: -0.1700

Data Index: 2355447 (Open Web Text)

Max Activating Token Index: 622